Collaborative Research: SaTC: EDU: Fire and ICE: Raising Security Awareness through Experiential Learning Activities for Building Trustworthy Deep Learning-based Applications

协作研究:SaTC:EDU:火灾和 ICE:通过体验式学习活动提高安全意识,构建值得信赖的基于深度学习的应用程序

基本信息

  • 批准号:
    2244220
  • 负责人:
  • 金额:
    $ 22万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2023
  • 资助国家:
    美国
  • 起止时间:
    2023-07-01 至 2026-06-30
  • 项目状态:
    未结题

项目摘要

In privacy-sensitive and safety-critical applications, deep learning models are increasingly accepted and utilized. This trend is bound to continue: many open-source frameworks and tools from online code repositories are embedded with deep learning modules. However, many deep learning models contain hidden weaknesses that could be exploited by attacks, posing significant risks to user privacy and safety. It is essential, therefore, to raise security awareness among college students, who are the future data engineering practitioners, and equip them with knowledge and strategies for designing trustworthy, deep learning based applications. This project responds to the urgent need in three critical areas: integrity, confidentiality and equity (ICE). A series of easy-to-implement experiential learning activities concretize learners’ awareness of potential vulnerabilities in deep learning models and enhance their ability to build secure applications of their own. These activities are expressly designed for learners with little prior knowledge, and are streamlined to reduce preparation time and cost for the instructor. The activities’ flexibility maximizes the equitable dissemination of relevant knowledge that is critical to society. The investigators are especially mindful of the needs of minority and socio-economically disadvantaged student populations.A total of twelve learning activity sets address a wide array of issues arising in ICE areas. For data integrity, threats posed by adversarial examples, data poisoning, and backdoor hidden features are tackled. The emphasis on experiential learning allows learners to become acquainted with the process and effects of attacks before learners are equipped with strategies and trained to implement proper defense. To enhance confidentiality, learners first encounter at least two potential sources of privacy leakage, dataset overfitting and abusive querying, and are then taught preventative countermeasures. Both sample biases and algorithmic biases in deep learning models are addressed in the learning activities. Artificial intelligence and deep learning constitute a fast-developing field, and educators must keep pace. The project enriches the supply of educational tools by introducing recent discoveries in the field, including those made by the investigators themselves.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
在隐私敏感和安全关键的应用中,深度学习模型越来越被接受和利用,这种趋势必将持续下去:许多来自在线代码存储库的开源框架和工具都嵌入了深度学习模块。因此,提高作为未来数据工程实践者的大学生的安全意识,并为他们提供设计知识和策略是至关重要的。该项目是值得信赖的、基于深度学习的应用程序。满足了完整性、保密性和公平性(ICE)三个关键领域的迫切需求。一系列易于实施的体验式学习活动具体化了学习者对深度学习模型潜在漏洞的认识,并增强了他们构建安全应用程序的能力。这些活动是专门为先验知识很少的学习者设计的,并且经过简化,以减少教师的准备时间和成本。这些活动的灵活性最大限度地提高了对社会至关重要的相关知识的公平传播。的需求总共十二个学习活动集解决了 ICE 领域出现的各种问题,包括对抗性示例、数据中毒和后门隐藏功能带来的威胁。在学习者配备策略并接受培训以实施适当的防御之前,学习可以让学习者熟悉攻击的过程和影响。为了增强保密性,学习者首先会遇到至少两个潜在的隐私泄露源:数据集过度拟合和滥用。人工智能和深度学习构成了一个快速发展的领域,教育工作者必须跟上步伐,丰富其供给。该奖项反映了 NSF 的法定使命,并通过使用基金会的智力价值和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Liran Ma其他文献

Temperature-controlled Friction Coefficient Lubricated by Liquid Crystal
液晶润滑温控摩擦系数
  • DOI:
    10.1080/02678292.2021.1944355
  • 发表时间:
    2021-07-09
  • 期刊:
  • 影响因子:
    2.2
  • 作者:
    Yuan Gao;Liran Ma;Jianbin Luo
  • 通讯作者:
    Jianbin Luo
Video Aficionado: We Know What You Are Watching
视频爱好者:我们知道您在看什么
  • DOI:
    10.1109/tmc.2020.3045730
  • 发表时间:
    2020-12-18
  • 期刊:
  • 影响因子:
    7.9
  • 作者:
    Jialing He;Zijian Zhang;Jian Mao;Liran Ma;B. Khoussainov;Rui Jin;Liehuang Zhu
  • 通讯作者:
    Liehuang Zhu
A Low Overhead and Stable Clustering Scheme for Crossroads in VANETs
车载自组网中十字路口低开销、稳定的聚类方案
A novel rate adaptation scheme for 802.11 networks
一种新颖的 802.11 网络速率自适应方案
Sliding direction dependence of stick-slip in finger friction
手指摩擦中粘滑运动的滑动方向依赖性
  • DOI:
    10.1016/j.triboint.2023.109141
  • 发表时间:
    2023-11-01
  • 期刊:
  • 影响因子:
    6.2
  • 作者:
    Zhonghuan Xiang;Yuanzhe Li;Xue Zhou;Pengpeng Bai;Yonggang Meng;Liran Ma;Yu Tian
  • 通讯作者:
    Yu Tian

Liran Ma的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Liran Ma', 18)}}的其他基金

SaTC: EDU: Collaborative: Advancing Cybersecurity Learning Through Inquiry-based Laboratories on a Container-based Virtualization Platform
SaTC:EDU:协作:通过基于容器的虚拟化平台上的探究实验室推进网络安全学习
  • 批准号:
    1912755
  • 财政年份:
    2019
  • 资助金额:
    $ 22万
  • 项目类别:
    Standard Grant
CyberTraining: CIP: Collaborative Research: Enhancing Mobile Security Education by Creating Eureka Experiences
网络培训:CIP:协作研究:通过创建 Eureka 体验加强移动安全教育
  • 批准号:
    1829553
  • 财政年份:
    2018
  • 资助金额:
    $ 22万
  • 项目类别:
    Standard Grant
EAGER: A Social and Context Aware Spectrum Management Framework for Heterogeneous Cognitive Radio Networks
EAGER:异构认知无线电网络的社交和情境感知频谱管理框架
  • 批准号:
    1352726
  • 财政年份:
    2013
  • 资助金额:
    $ 22万
  • 项目类别:
    Standard Grant

相似国自然基金

基于肿瘤病理图片的靶向药物敏感生物标志物识别及统计算法的研究
  • 批准号:
    82304250
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
肠道普拉梭菌代谢物丁酸抑制心室肌铁死亡改善老龄性心功能不全的机制研究
  • 批准号:
    82300430
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
社会网络关系对公司现金持有决策影响——基于共御风险的作用机制研究
  • 批准号:
    72302067
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
面向图像目标检测的新型弱监督学习方法研究
  • 批准号:
    62371157
  • 批准年份:
    2023
  • 资助金额:
    50 万元
  • 项目类别:
    面上项目
面向开放域对话系统信息获取的准确性研究
  • 批准号:
    62376067
  • 批准年份:
    2023
  • 资助金额:
    51 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: SaTC: CORE: Medium: Differentially Private SQL with flexible privacy modeling, machine-checked system design, and accuracy optimization
协作研究:SaTC:核心:中:具有灵活隐私建模、机器检查系统设计和准确性优化的差异化私有 SQL
  • 批准号:
    2317232
  • 财政年份:
    2024
  • 资助金额:
    $ 22万
  • 项目类别:
    Continuing Grant
Collaborative Research: NSF-BSF: SaTC: CORE: Small: Detecting malware with machine learning models efficiently and reliably
协作研究:NSF-BSF:SaTC:核心:小型:利用机器学习模型高效可靠地检测恶意软件
  • 批准号:
    2338302
  • 财政年份:
    2024
  • 资助金额:
    $ 22万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Using Intelligent Conversational Agents to Empower Adolescents to be Resilient Against Cybergrooming
合作研究:SaTC:核心:中:使用智能会话代理使青少年能够抵御网络诱骗
  • 批准号:
    2330940
  • 财政年份:
    2024
  • 资助金额:
    $ 22万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Using Intelligent Conversational Agents to Empower Adolescents to be Resilient Against Cybergrooming
合作研究:SaTC:核心:中:使用智能会话代理使青少年能够抵御网络诱骗
  • 批准号:
    2330941
  • 财政年份:
    2024
  • 资助金额:
    $ 22万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Differentially Private SQL with flexible privacy modeling, machine-checked system design, and accuracy optimization
协作研究:SaTC:核心:中:具有灵活隐私建模、机器检查系统设计和准确性优化的差异化私有 SQL
  • 批准号:
    2317233
  • 财政年份:
    2024
  • 资助金额:
    $ 22万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了